Empirical Loss Landscape Analysis of Neural Network Activation Functions

Author:

Bosman Anna Sergeevna1ORCID,Engelbrecht Andries23ORCID,Helbig Marde4ORCID

Affiliation:

1. Computer Science, University of Pretoria, Pretoria, Gauteng, South Africa

2. University of Stellenbosch, Stellenbosch, South Africa

3. Center for Applied Mathematics and Bioinformatics, Gulf University for Science and Technology, Kuwait City, Kuwait

4. School of Information and Communication Technology, Griffith University, Southport, Australia

Funder

National Research Foundation

Publisher

ACM

Reference35 articles.

1. Raman Arora , Amitabh Basu , Poorya Mianjy , and Anirbit Mukherjee . 2018 . Understanding deep neural networks with rectified linear units . In Proceedings of the International Conference on Learning Representations . Vancouver, Canada, 1--17. Raman Arora, Amitabh Basu, Poorya Mianjy, and Anirbit Mukherjee. 2018. Understanding deep neural networks with rectified linear units. In Proceedings of the International Conference on Learning Representations. Vancouver, Canada, 1--17.

2. Visualising basins of attraction for the cross-entropy and the squared error neural network loss functions

3. Search space boundaries in neural network error landscape analysis

4. Progressive gradient walk for neural network fitness landscape analysis

5. Loss Surface Modality of Feed-Forward Neural Network Architectures

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Characterising Deep Learning Loss Landscapes with Local Optima Networks;2024 IEEE Congress on Evolutionary Computation (CEC);2024-06-30

2. Fitness Landscape Analysis of Product Unit Neural Networks;Algorithms;2024-06-04

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3